Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning

• URL: http://arxiv.org/abs/2503.18432v1
• Date: Mon, 24 Mar 2025 08:28:34 GMT
• Title: Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning
• Authors: Junsong Li, Jie Zhou, Yutao Yang, Bihao Zhan, Qianjun Pan, Yuyang Ding, Qin Chen, Jiang Bo, Xin Lin, Liang He,
• Abstract summary: We propose a reinforcement learning (RL)-based method to boost large language model (LLM) for step-level automatic math correction, named StepAMC.<n> Particularly, we convert the step-level automatic math correction within the text classification task into an RL problem to enhance the reasoning capabilities of LLMs.
• Score: 29.97121243044881
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic math correction aims to check students' solutions to mathematical problems via artificial intelligence technologies. Most existing studies focus on judging the final answer at the problem level, while they ignore detailed feedback on each step in a math problem-solving process, which requires abilities of semantic understanding and reasoning. In this paper, we propose a reinforcement learning (RL)-based method to boost large language model (LLM) for step-level automatic math correction, named StepAMC. Particularly, we convert the step-level automatic math correction within the text classification task into an RL problem to enhance the reasoning capabilities of LLMs. Then, we design a space-constrained policy network to improve the stability of RL. Then, we introduce a fine-grained reward network to convert the binary human feedback into a continuous value. We conduct extensive experiments over two benchmark datasets and the results show that our model outperforms the eleven strong baselines.

Related papers

• A Survey on Mathematical Reasoning and Optimization with Large Language Models [0.5439020425819]
  Recent advancements in Large Language Models (LLMs) have significantly improved AI-driven mathematical reasoning, theorem proving, and optimization techniques. This survey explores the evolution of mathematical problem-solving in AI, from early statistical learning approaches to modern deep learning and transformer-based methodologies.
  arXiv  Detail & Related papers  (2025-03-22T10:49:32Z)
• MathMistake Checker: A Comprehensive Demonstration for Step-by-Step Math Problem Mistake Finding by Prompt-Guided LLMs [13.756898876556455]
  We propose a novel system, MathMistake Checker, to automate step-by-step mistake finding in mathematical problems with lengthy answers.<n>The system aims to simplify grading, increase efficiency, and enhance learning experiences from a pedagogical perspective.
  arXiv  Detail & Related papers  (2025-03-06T10:19:01Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Learning for Cross-Layer Resource Allocation in MEC-Aided Cell-Free Networks [71.30914500714262]
  Cross-layer resource allocation over mobile edge computing (MEC)-aided cell-free networks can sufficiently exploit the transmitting and computing resources to promote the data rate. Joint subcarrier allocation and beamforming optimization are investigated for the MEC-aided cell-free network from the perspective of deep learning.
  arXiv  Detail & Related papers  (2024-12-21T10:18:55Z)
• Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning [62.984693936073974]
  Value-based reinforcement learning can learn effective policies for a wide range of multi-turn problems.<n>Current value-based RL methods have proven particularly challenging to scale to the setting of large language models.<n>We propose a novel offline RL algorithm that addresses these drawbacks, casting Q-learning as a modified supervised fine-tuning problem.
  arXiv  Detail & Related papers  (2024-11-07T21:36:52Z)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [49.362750475706235]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks.<n>We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model.<n> Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners [23.713779973116733]
  Self-correction is a method that can stimulate the potential reasoning abilities of large language models (LLMs)<n>We propose S$3$c-Math, which are able to perform Spontaneous Step-level Self-correction for Mathematical reasoning.
  arXiv  Detail & Related papers  (2024-09-03T01:40:21Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• AlphaMath Almost Zero: Process Supervision without Process [6.318873143509028]
  We propose an innovative framework, AlphaMath, that bypasses the need for process annotations by leveraging Monte Carlo Tree Search (MCTS) This framework focuses on unleashing the potential of a well-pretrained LLM to autonomously enhance its mathematical reasoning. The experimental results on both in-domain and out-of-domain datasets demonstrate that even without GPT-4 or human-annotated process supervision, our AlphaMath framework achieves comparable or superior results to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-06T15:20:30Z)
• Reinforcement Learning Problem Solving with Large Language Models [0.0]
  Large Language Models (LLMs) have an extensive amount of world knowledge, and this has enabled their application in various domains to improve the performance of Natural Language Processing (NLP) tasks. This has also facilitated a more accessible paradigm of conversation-based interactions between humans and AI systems to solve intended problems. We show the practicality of our approach through two detailed case studies for "Research Scientist" and "Legal Matter Intake"
  arXiv  Detail & Related papers  (2024-04-29T12:16:08Z)
• From Large to Tiny: Distilling and Refining Mathematical Expertise for Math Word Problems with Weakly Supervision [12.023661884821554]
  We introduce an innovative two-stage framework that adeptly transfers mathematical Expertise from large to tiny language models. Our method fully leverages the semantic understanding capabilities during the searching 'problem-equation' pair. It demonstrates significantly improved performance on the Math23K and Weak12K datasets compared to existing small model methods.
  arXiv  Detail & Related papers  (2024-03-21T13:29:54Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions [47.83142414018448]
  We focus on two popular reasoning tasks: arithmetic reasoning and code generation. We introduce (i) a general ontology of perturbations for math and coding questions, (ii) a semi-automatic method to apply these perturbations, and (iii) two datasets. We show a significant performance drop across all the models against perturbed questions.
  arXiv  Detail & Related papers  (2024-01-17T18:13:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.